Controlled Memory Interference in Continual LLM Agents

• URL: http://arxiv.org/abs/2608.07622v1
• Date: Fri, 07 Aug 2026 09:46:19 GMT
• Title: Controlled Memory Interference in Continual LLM Agents
• Abstract summary: Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and evolve through accumulated experience.<n>Existing systems mainly emphasize memory construction and relevance-based retrieval, but several memories may remain simultaneously relevant while differing in state, temporal validity, or authority.<n>We introduce Controlled Memory Interference (CMI), a controlled diagnostic and data-generation framework for studying how agent memory evolves under different memory relationships.
• Score: 19.630594179909156
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and evolve through accumulated experience. Yet memory evolution is not simply a process of storing more information: new experiences may reinforce, revise, or interfere with existing memory states. Existing systems mainly emphasize memory construction and relevance-based retrieval, but several memories may remain simultaneously relevant while differing in state, temporal validity, or authority. We introduce Controlled Memory Interference (CMI), a controlled diagnostic and data-generation framework for studying how agent memory evolves under different memory relationships. Across controlled memory evolution, benign accumulation has limited effects, whereas relationship-specific interference sharply suppresses update plasticity with little stability gain, either by blocking target-memory exposure or by disrupting its downstream use. Lexical and Dense retrieval exhibit distinct interference pathways, while poisoning is more sensitive to update-authority cues than to recency alone. Beyond diagnosis, CMI provides targeted examples for interference-aware memory learning, improving the distinction between valid updates and interference-inducing memories while preserving performance on original memory tasks. These findings show that memory evolution is shaped not only by memory scale, but also by interactions among accumulated experiences. More broadly, memory interference emerges as an important factor for reliable continual agent memory systems.

Related papers

• Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents [39.55670043123564]
  Existing memory systems update memory when new information arrives.<n>Retrieval feedback is rarely exploited to reorganize memory for future access continuously.<n>We propose textbfREALM, a framework for continually evolving long-term memory in LLM agents.
  arXiv  Detail & Related papers  (2026-09-13T05:17:37Z)
• Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory [21.71796784567462]
  Memory mechanisms that retain, transform, or expose more information can affect both benign utility and susceptibility to memory poisoning.<n>We present textscMemGauge, a controllable framework that separately varies writing admission, management policy, and retrieval exposure under poisoned conditions.
  arXiv  Detail & Related papers  (2026-08-31T02:57:08Z)
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction [72.1620416874118]
  Multimodal large language models are increasingly deployed as long-horizon agents.<n>Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions.<n>We formulate multimodal agent memory as an Action-World Interaction Loop with an observable four-stage lifecycle.
  arXiv  Detail & Related papers  (2026-05-28T04:27:20Z)
• MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models [56.31411457917676]
  We introduce MemGuard, a type-aware memory framework that preserves functional memory boundaries during memory construction and retrieval.<n>Across hallucination and long-horizon conversation benchmarks, MemGuard improves memory reliability by up to 28.27% while retrieving up to 5.8x fewer memory tokens than prior methods.
  arXiv  Detail & Related papers  (2026-05-27T06:04:19Z)
• MemEvoBench: Benchmarking Memory MisEvolution in LLM Agents [78.95081012334116]
  Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks.<n> contaminated or biased memory accumulation can trigger abnormal agent behaviors.<n>MemeEvoBench is the first benchmark evaluating memory safety in LLM agents against adversarial memory injection, noisy tool outputs, and biased feedback.
  arXiv  Detail & Related papers  (2026-04-17T07:29:52Z)
• Memory Bear AI Memory Science Engine for Multimodal Affective Intelligence: A Technical Report [3.9870633524104107]
  Memory Bear AI Memory Science Engine is a memory-centered framework for multimodal affective intelligence.<n>It organizes processing through structured memory formation, working-memory aggregation, long-term consolidation, memory-driven retrieval, dynamic fusion calibration, and continuous memory updating.<n> Experimental results show consistent gains over comparison systems across benchmark and business-grounded settings.
  arXiv  Detail & Related papers  (2026-03-18T10:23:00Z)
• FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory [4.608947574766633]
  We propose FadeMem, a biologically-inspired agent memory architecture that incorporates active forgetting mechanisms mirroring human cognitive efficiency.<n>Experiments on Multi-Session Chat, LoCoMo, and LTI-Bench demonstrate superior multi-hop reasoning and retrieval with 45% storage reduction.
  arXiv  Detail & Related papers  (2026-01-26T16:12:54Z)
• Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management [49.71055327567513]
  We argue that memory management should be viewed as a sequential decision-making problem under uncertainty.<n>Our contribution is not a new algorithm, but a principled reframing that clarifies the limitations of approaches.
  arXiv  Detail & Related papers  (2025-12-25T08:23:03Z)
• Memory Bear AI A Breakthrough from Memory to Cognition Toward Artificial General Intelligence [1.9075119881212463]
  Large language models (LLMs) face inherent limitations in memory.<n>This paper proposes the Memory Bear system, which constructs a human-like memory architecture grounded in cognitive science principles.
  arXiv  Detail & Related papers  (2025-12-17T06:06:18Z)
• Memory in the Age of AI Agents [217.9368190980982]
  This work aims to provide an up-to-date landscape of current agent memory research.<n>We identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory.<n>To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks.
  arXiv  Detail & Related papers  (2025-12-15T17:22:34Z)
• MemVerse: Multimodal Memory for Lifelong Learning Agents [35.218549149012844]
  We introduce MemVerse, a model-agnostic, plug-and-play memory framework.<n>MemVerse bridges fast parametric recall with hierarchical retrieval-based memory.<n>It enables scalable and adaptive multimodal intelligence.
  arXiv  Detail & Related papers  (2025-12-03T10:06:14Z)
• MemGen: Weaving Generative Latent Memory for Self-Evolving Agents [57.1835920227202]
  We propose MemGen, a dynamic generative memory framework that equips agents with a human-esque cognitive faculty.<n>MemGen enables agents to recall and augment latent memory throughout reasoning, producing a tightly interwoven cycle of memory and cognition.
  arXiv  Detail & Related papers  (2025-09-29T12:33:13Z)
• Augmented Replay Memory in Reinforcement Learning With Continuous Control [1.6752182911522522]
  Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion increases the agent's state space enabling it to scale up to a more complex problems but also increases the risk of forgetting by learning on redundant or conflicting data. To improve the approximation of a large amount of data, a random mini-batch of the past experiences that are stored in the replay memory buffer is often replayed at each learning step.
  arXiv  Detail & Related papers  (2019-12-29T20:07:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.